cs.AI（2025-07-29）

📊 共 24 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (12 🔗4) 支柱九：具身大模型 (Embodied Foundation Models) (10) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (12 篇)

#题目一句话要点标签🔗⭐
1 MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions MoHoBench：通过无法回答的视觉问题评估多模态大语言模型的诚实性 preference learning large language model multimodal ✅
2 Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security 提出SecTOW，通过强化学习迭代攻防训练提升多模态大模型的安全性。 reinforcement learning large language model multimodal
3 UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding UI-AGILE：通过强化学习和精确推理时定位提升GUI智能体性能 reinforcement learning large language model multimodal ✅
4 Large Language Model-Based Framework for Explainable Cyberattack Detection in Automatic Generation Control Systems 提出基于大语言模型的网络攻击可解释检测框架，用于自动发电控制系统 MAE large language model
5 ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge ChemDFM-R：通过原子化化学知识增强的化学推理大语言模型 reinforcement learning distillation large language model
6 Assistax: A Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Robotics Assistax：一个用于辅助机器人的硬件加速强化学习基准测试平台 reinforcement learning ✅
7 CoEx -- Co-evolving World-model and Exploration CoEx：通过协同演化的世界模型和探索解决LLM智能体规划中的知识偏差问题 world model
8 Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items 提出MMSC框架，利用多模态关系学习推断可替代和互补商品，解决用户行为噪声和数据稀疏性问题。 representation learning
9 Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks 提出基于领域知识增强的LLM框架，用于5G无线网络根因分析 reinforcement learning large language model
10 EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity 提出EDGE-GRPO算法，通过熵驱动优势函数和引导式纠错解决GRPO中的优势坍塌问题 reinforcement learning large language model ✅
11 What Does it Mean for a Neural Network to Learn a "World Model"? 为神经网络学习“世界模型”提出可操作的评估标准 world model
12 Exploring the Stratified Space Structure of an RL Game with the Volume Growth Transform 利用体积增长变换探索强化学习游戏中Transformer模型的层化空间结构 reinforcement learning PPO

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
13 Compression Strategies for Efficient Multimodal LLMs in Medical Contexts 针对医疗场景，提出高效压缩策略优化多模态LLM，降低计算成本。 large language model multimodal
14 Can large language models assist choice modelling? Insights into prompting strategies and current models capabilities 探索大语言模型在选择建模中的应用：提示策略与模型能力分析 large language model chain-of-thought
15 Pathology Foundation Models are Scanner Sensitive: Benchmark and Mitigation with Contrastive ScanGen Loss 提出ScanGen以缓解病理模型的扫描仪偏差问题 foundation model
16 When Truthful Representations Flip Under Deceptive Instructions? 研究欺骗性指令下LLM内部表征的翻转现象，揭示不诚实行为的特征。 large language model
17 UserBench: An Interactive Gym Environment for User-Centric Agents UserBench：一个以用户为中心的交互式环境，用于评估用户导向型Agent large language model
18 Promoting Online Safety by Simulating Unsafe Conversations with LLMs 利用LLM模拟不安全对话，提升在线安全意识 large language model
19 MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automation MapAgent：利用轨迹构建的记忆增强规划，实现移动设备任务自动化 large language model
20 Libra: Large Chinese-based Safeguard for AI Content Libra-Guard：针对中文LLM的安全保障系统，并构建了首个中文安全评测基准。 large language model
21 The Impact of Foundational Models on Patient-Centric e-Health Systems 利用大型语言模型评估以患者为中心的电子健康系统中人工智能的成熟度 large language model
22 DualSG: A Dual-Stream Explicit Semantic-Guided Multivariate Time Series Forecasting Framework 提出DualSG框架，利用大语言模型语义指导提升多元时间序列预测精度。 large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
23 MultiEditor: Controllable Multimodal Object Editing for Driving Scenarios Using 3D Gaussian Splatting Priors MultiEditor：利用3D高斯先验实现自动驾驶场景下可控的多模态物体编辑 3D gaussian splatting 3DGS gaussian splatting

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
24 Strategic Deflection: Defending LLMs from Logit Manipulation 提出战略偏转(SDeflection)防御LLM的logit操控攻击 manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页